Performance Consistency

We've been looking at performance consistency since the Intel SSD DC S3700 review in late 2012 and it has become one of the cornerstones of our SSD reviews. Back in the days many SSD vendors were only focusing on high peak performance, which unfortunately came at the cost of sustained performance. In other words, the drives would push high IOPS in certain synthetic scenarios to provide nice marketing numbers, but as soon as you pushed the drive for more than a few minutes you could easily run into hiccups caused by poor performance consistency.

Once we started exploring IO consistency, nearly all SSD manufacturers made a move to improve consistency and for the 2015 suite, I haven't made any significant changes to the methodology we use to test IO consistency. The biggest change is the move from VDBench to Iometer 1.1.0 as the benchmarking software and I've also extended the test from 2000 seconds to a full hour to ensure that all drives hit steady-state during the test.

For better readability, I now provide bar graphs with the first one being an average IOPS of the last 400 seconds and the second graph displaying the standard deviation during the same period. Average IOPS provides a quick look into overall performance, but it can easily hide bad consistency, so looking at standard deviation is necessary for a complete look into consistency.

I'm still providing the same scatter graphs too, of course. However, I decided to dump the logarithmic graphs and go linear-only since logarithmic graphs aren't as accurate and can be hard to interpret for those who aren't familiar with them. I provide two graphs: one that includes the whole duration of the test and another that focuses on the last 400 seconds of the test to get a better scope into steady-state performance.

Steady-State 4KB Random Write Performance

TLC SSDs in general don't perform well under sustained random workloads and the Trion 100 is no exception. It seems that with TLC SSDs we have to accept a drop from 5K to 2-3K IOPS, which is still fine for basic client workloads since most SSDs from 3-4 years ago couldn't even match that.

Steady-State 4KB Random Write Consistency

The consistency isn't great either, but it's not particularly poor either when compared agains Silicon Motion drives.

OCZ Trion 100
Default
25% Over-Provisioning

Looking at the performance over time, we can see that the baseline performance hovers at about 1,000 IOPS with frequent peaks occuring at 5K to 10K IOPS. That's actually very similar to the Neutron XT's (Phison S10) graph because the baseline is also 1,000 IOPS, although the peaks are higher and more frequent, but it further reassures that the underlying firmware architecture is similar. Increasing over-provisioning doesn't increase the baseline performance, but it does make peak performance moments more frequent and higher (from 10K IOPS to 25K IOPS). 

OCZ Trion 100
Default
25% Over-Provisioning
Introduction, The Drives & The Test AnandTech Storage Bench - The Destroyer
POST A COMMENT

65 Comments

View All Comments

  • ocz_tuff_bunny - Friday, July 17, 2015 - link

    Hi sonny73n,
    Thank you for your comment. You are right there is still a price gap between SSD and HDD. With the introduction of Trion 100 and OCZ adjusting prices quickly with the market trend we hope to narrow that price gap and making this SSD affordable for the mass market. Thank you again for your feedback and words of encouragement.
    Reply
  • Ryan Smith - Saturday, July 11, 2015 - link

    In the interest of transparency, one comment has been removed for profanity and racism.

    As a reminder to all readers, racism and profanity are not welcome nor tolerated in the AnandTech comments.
    Reply
  • sonny73n - Friday, July 10, 2015 - link

    "considering the Samsung alternative" Really?

    I have an 840 EVO from not too long ago in my laptop and I'm so ready to send it to the trash. There's an article here about its problems which Samsung have been incapable of fixing with new firmware updates that you should take a look on. Beside, I consider it's cheating when Samsung use my system RAM as cache for their SSD. My next SSD definitely won't be Samsung's.
    Reply
  • NvidiaWins - Friday, July 10, 2015 - link

    Samsung is terrible SSD manufactuer, in fact Intel was the only SSD that passed Torture Testing
    http://www.extremetech.com/computing/173887-ssd-st...
    Reply
  • ggathagan - Tuesday, July 14, 2015 - link

    I've heard of a "one trick pony" before.
    I've never seen a "one link troll" before now.
    The linked article doesn't even involve Samsung SSD's.
    Not only are you a troll, you're an ignorant troll.
    Reply
  • shadowjk - Saturday, July 11, 2015 - link

    Toshiba's silence on the drive probably makes enthusiasts nervous about this drive, if they weren't already nervous considering OCZ's heritage... This might be a tough sell indeed. Reply
  • jabber - Sunday, July 12, 2015 - link

    To be honest SSDs like these should be marketed cheap and largely aimed at SATA I/II kit owners. A lot of kit out there is still only SATA II and to be honest the cheapest SSD out there will push 260MBps all day long and still feel light speed fast compared to the 5400rpm 65MBps HDD it replaced. No point bothering trying to say they compete for SATA III owners. Hence why I buy a lot of the Kingston V300 SSDs. Most here wouldnt touch them but they are reliable, the cheapest and will push a SATA II laptop or PC to its max. Reply
  • romrunning - Thursday, July 9, 2015 - link

    "OCZ wasn't involved in the development of the Trion 100, but it did help Toshiba to validate the drive. "

    With OCZ's past history, I found that statement to be quite humorous! :)
    Reply
  • TheWrongChristian - Thursday, July 9, 2015 - link

    Yeah. I was expecting the relationship to work the other way round. Reply
  • The_Assimilator - Thursday, July 9, 2015 - link

    It makes sense, since OCZ has far more SSD experience than Toshiba; that's why Toshiba bought them. Unfortunately it looks like OCZ's "validation" procedures haven't changed much from the days of the Vertex 2 debacle. Reply

Log in

Don't have an account? Sign up now